A flow-matching TTS model with pseudo-label training enables continuous disentangled control of vocal effort, articulation, and word-level emphasis to replicate Lombard effect intelligibility gains in noise.
Analysis and syn- thesis of hypo and hyperarticulated speech,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS
A flow-matching TTS model with pseudo-label training enables continuous disentangled control of vocal effort, articulation, and word-level emphasis to replicate Lombard effect intelligibility gains in noise.